Live data from Hacker News

AI real-time human full-body photo generator

generated.photos

1–10 of 421 posts

Re: AI real-time human full-body photo generator

#6
We know about all of the potential harms that deepfakes can cause, the problems with inherent bias in training data, etc.

Creating/publicising a tool that winks at these issues (consider the difference between the poses offered for 'male' and 'female' bodies) but does nothing to mitigate them - and a lot to enable them - is irresponsible at best.

Re: AI real-time human full-body photo generator

#9
If you're wondering how it's so fast and cheap and they can generate variants so easily, it's because they're using GANs (see the footer). GANs are way faster than diffusion models because they generate the image in a single forward pass and their true latent space encoding makes editing a breeze.

(And if you're wondering how it can look so good when 'everyone knows GANs don't work because they're too unstable', a widespread myth, repeated by many DL researchers who ought to know better, GANs can scale to high-quality realistic images on billion-image scale datasets, and become more, not less, stable with scale, like many things in deep reinforcement learning. See for example BigGAN on JFT-300m https://arxiv.org/pdf/1809.11096.pdf#page=8&org=deepmind , GigaGAN https://arxiv.org/abs/2303.05511 , Projected GAN https://arxiv.org/abs/2111.01007 , StyleGAN-XL https://arxiv.org/abs/2202.00273 , or Tensorfork's chaos runs https://gwern.net/gan#tensorfork-chaos-runs . 'Computing is a pop culture'...)

Re: AI real-time human full-body photo generator

#10
post #7

> “If you want to use images produced by Human Generator in commercial projects, contact us.” If there is no copyright in AI-generated images, then how can they possibly enforce this?

There haven't been any solid rulings on the copyright validity of human-driven AI generation yet. There have been a few cases, but they've been muddied by complicating factors (not a human doing the generation - that is, autonomous generation - or the generation being used as a base work for something else).

Additionally, even if there's no copyright, the terms of service may still apply separately (see OpenAI disallowing training a competitor model on output from OpenAI models)

Post reply on HN